Hybrid Approach to Classification of DDoS Attacks on a Computer Network Infrastructure
Bibliographic record
Abstract
The advancement in technology, its ease of use, and the competitive nature of its deployment in business operations have led to the wide spread of networking systems globally, and Ghana is not an exception. Most business operations and even personal activities are now conducted online leading to increased network connectivity, access to networked resources, and the corresponding cyber-attacks on these network systems. Distributed Denial-of-Service (DDoS) is one of the sophisticated attacks in the cyberspace. In DDOs, the attacker floods the network with massive and unsolicited traffic, causing the network infrastructure to exhaust all its resources in responding to the attacker’s request, thereby denying access to legitimate users of such resources. In this study, we designed and implemented a hybrid deep learning model (CRNN-Infusion) for detection and classification of DDoS attacks. Our model utilized the CNN, and RNN models, with the CICDDoS2019 dataset obtained from the Canadian Institute of Cybersecurity (CIC) for its training, with Random Search Hyperparameter Tuning (RSHT) and Feature Selection (FS) techniques for model efficiency and dimensionality reduction. Cybersecurity (CIC) for the model’s training, with Random Search Hyperparameter Tuning (RSHT) and FS techniques for model efficiency and dimensionality reduction. The results showed that, our proposed model is a better classifier for DDoS attacks compared to other deep learning (DL) models trained on the same dataset. With the highest accuracy of 98.92%, hybrid deep learning models are suitable for detecting and classifying DDoS attacks on network infrastructures. The findings point out that, with the appropriate choice of feature selection and hyperparameter tuning techniques, hybrid deep learning models perform optimally, with 98.92% accuracy, 99.02% precision, 98.92% recall, and 98.93% F1 score for our proposed model.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".